Timezone: »

Neurosymbolic Transformers for Multi-Agent Communication
Jeevana Priya Inala · Yichen Yang · James Paulos · Yewen Pu · Osbert Bastani · Vijay Kumar · Martin Rinard · Armando Solar-Lezama

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #967

We study the problem of inferring communication structures that can solve cooperative multi-agent planning problems while minimizing the amount of communication. We quantify the amount of communication as the maximum degree of the communication graph; this metric captures settings where agents have limited bandwidth. Minimizing communication is challenging due to the combinatorial nature of both the decision space and the objective; for instance, we cannot solve this problem by training neural networks using gradient descent. We propose a novel algorithm that synthesizes a control policy that combines a programmatic communication policy used to generate the communication graph with a transformer policy network used to choose actions. Our algorithm first trains the transformer policy, which implicitly generates a "soft" communication graph; then, it synthesizes a programmatic communication policy that "hardens" this graph, forming a neurosymbolic transformer. Our experiments demonstrate how our approach can synthesize policies that generate low-degree communication graphs while maintaining near-optimal performance.

Author Information

Jeevana Priya Inala (MIT)
Yichen Yang (MIT)
James Paulos (University of Pennsylvania)
Yewen Pu (Autodesk)
Osbert Bastani (University of Pennysylvania)
Vijay Kumar (University of Pennsylvania)
Martin Rinard (MIT)
Armando Solar-Lezama (MIT)

More from the Same Authors